CN115270506A - Method and system for predicting passing time of people going upstairs along stairs - Google Patents
Method and system for predicting passing time of people going upstairs along stairs Download PDFInfo
- Publication number
- CN115270506A CN115270506A CN202210982696.7A CN202210982696A CN115270506A CN 115270506 A CN115270506 A CN 115270506A CN 202210982696 A CN202210982696 A CN 202210982696A CN 115270506 A CN115270506 A CN 115270506A
- Authority
- CN
- China
- Prior art keywords
- model
- neural network
- crowd
- training
- stair
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 63
- 238000013528 artificial neural network Methods 0.000 claims abstract description 45
- 238000004088 simulation Methods 0.000 claims abstract description 34
- 238000010845 search algorithm Methods 0.000 claims abstract description 19
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 25
- 210000002569 neuron Anatomy 0.000 claims description 15
- 230000001174 ascending effect Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005610 quantum mechanics Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting the passing time of a crowd going upstairs along a stair, which belong to the field of predicting the passing time and are used for constructing a three-dimensional simulation model of a stair scene; putting the simulation individual into a three-dimensional simulation model, and constructing a training set of a BP neural network model; training the BP neural network model optimized by the atomic orbit search algorithm by using a training set; inputting the gradient, height, width, individual expected speed and radius of the stair to be predicted and the number of the crowd into the trained model to obtain the passing time of the corresponding crowd going up the stair; the invention predicts the passing time of the crowd going up the stairs by using the BP neural network optimized by the atomic orbit search algorithm, has high prediction precision, fully considers the influence of the gradient, the height, the width, the individual expected speed and radius of the stairs and the number of the crowd on the passing time of the crowd going up the stairs, is not only beneficial to the individual management and control in the peak period of passenger flow, but also can improve the escape efficiency of the individuals in public places in emergency.
Description
Technical Field
The invention belongs to the field of traffic time prediction, and particularly relates to a method and a system for predicting the traffic time of a crowd ascending along a stair.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The prediction of the passage time of the crowd going up the stairs has important significance for the management and control of the passenger flow in the public place; particularly, subway stations built underground have the characteristics of large passenger flow and centralized equipment, and the subway stations are often provided with large passenger flow in the morning and evening at peak; the stairs in the subway station are usually long and narrow, and when the passenger flow in the subway station is large or emergency evacuation is needed, the individual passage on the stairs is very difficult, which brings potential safety hazards for selecting the individual going out of the subway.
The prior research aiming at the passage time of individuals in public places (such as subway stations) going up along stairs has the following problems:
(1) The passing time of the individual on the stairs is judged only through the crowd density, and the influence of the individual expected speed and radius on the individual passing time is not considered;
(2) The influence of the gradient, the height and the width of the stair on the individual passing time is not considered;
(3) The related research results are less, and the reliability is not high;
(4) The same type of prediction methods usually obtain a prediction formula through data fitting, and the accuracy is not high.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method and a system for predicting the passing time of the crowd going up the stairs, wherein the BP neural network optimized by the atomic orbit search algorithm is utilized to predict the passing time of the crowd going up the stairs, the prediction precision is high, and the influence of the gradient, the height, the width, the individual expected speed and radius and the crowd quantity on the passing time of the crowd going up the stairs is fully considered, so that the method and the system not only are beneficial to individual control in the peak period of passenger flow, but also can improve the escape efficiency of individuals in public places in emergency.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the invention provides a method for predicting the passing time of a crowd going up a stair in a first aspect;
a method for predicting the passing time of a crowd going up stairs comprises the following steps:
building a three-dimensional simulation model of a stair scene;
putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
and inputting the gradient, height, width, individual expected speed and radius of the stair to be predicted and the number of the crowd to be predicted into the trained model to obtain the passing time of the corresponding crowd going up the stair.
Furthermore, an individual motion simulation software based on a social force model is adopted to construct a three-dimensional simulation model of the stair scene.
Furthermore, the simulation of various scenes is to change the gradient, height, width, individual expected speed, radius and the number of people in the simulation for many times to obtain corresponding passing time.
Furthermore, the atomic orbit search algorithm is based on the atomic orbit principle, and simulates the action between electrons in the atomic orbit to iterate the solution, the weight and the threshold of the neural network obtained by the traditional BP neural network are used as the attributes of the electrons in the atomic orbit, and the error is used as the function value of the probability density of the corresponding electron.
Further, training the BP neural network model optimized by the atomic orbit search algorithm specifically comprises:
(1) Determining the number of input layer neurons and the number of output layer neurons of the BP neural network according to the number of the input features and the number of the predicted features, defining the number of hidden layer layers to be 1 according to the Kolmogorov theorem, and determining the number of neurons in the hidden layers, namely, a total three-layer neural network;
(2) Setting an initial weight and a threshold of a neural network;
(3) Carrying out training by bringing the training set into a BP neural network to obtain a weight value, a threshold value and a corresponding error after the training is finished, namely finishing the training of the BP neural network once, and taking the result as an electron of a certain layer of the atomic orbit;
(4) Repeating the training of the BP neural network for o times to obtain o groups of weights, thresholds and corresponding errors for completing the training, so as to obtain o electrons to form all candidate solutions in each layer of the atomic orbit;
(5) And taking the v candidate solutions as candidate solutions in a certain layer of the atomic orbit, and calculating to obtain a candidate solution corresponding to the highest probability density function value (the minimum value of the objective function), namely the optimal weight and the optimal threshold of the model, thereby completing the training of the model.
Further, the number of the input features is the number of types of the stair slope, the height, the width, the expected speed and the radius of the pedestrian and the number of the crowd, and the number of the predicted features is 1, namely, only the passing time of the crowd going up the stair is predicted.
Further, the Kolmogorov theorem indicates that the three-layer neural network can map a nonlinear function with arbitrary precision.
In a second aspect of the invention, a system for predicting the transit time of a group of people traveling up stairs is provided.
A system for predicting the passing time of a crowd ascending along stairs comprises a model building module, a training set building module, a model training module and a prediction result module;
a model building module configured to: building a three-dimensional simulation model of a stair scene;
a training set construction module configured to: putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
a model training module configured to: training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
a prediction results module configured to: and inputting the gradient, height, width, individual expected speed and radius of the stair to be predicted and the number of the crowd to be predicted into the trained model to obtain the passing time of the corresponding crowd going up the stair.
A third aspect of the invention provides a computer-readable storage medium, on which a program is stored, which program, when executed by a processor, performs the steps in a method for predicting a transit time for a person travelling up stairs according to the first aspect of the invention.
A fourth aspect of the present invention provides an electronic device, comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for predicting the passage time of a crowd going up stairs according to the first aspect of the present invention.
The above one or more technical solutions have the following beneficial effects:
the invention utilizes the BP neural network optimized by the atomic orbit search algorithm to predict the passing time of the crowd going up the stairs, has high prediction precision, fully considers the influence of the gradient, the height, the width, the individual expected speed and radius of the stairs and the number of the crowd on the passing time of the crowd going up the stairs, is not only beneficial to the individual management and control in the peak period of passenger flow, but also can provide a node time basis for the formulation of an individual escape route in a public place in an emergency, and improves the evacuation efficiency.
The invention adopts the simulation software based on the social force model to obtain the training set of the model, can simulate various scenes, obtains a large amount of training set data under each scene in a short time and improves the efficiency.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of the method of the first embodiment.
Fig. 2 is a three-dimensional simulation model diagram of the staircase in the first embodiment.
FIG. 3 is a three-dimensional simulation model diagram of a staircase with simulated individuals according to the first embodiment.
Fig. 4 is a system configuration diagram of the second embodiment.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
The embodiment takes the stairs in the subway station as an example to describe in detail the process of the method for predicting the transit time of the crowd ascending along the stairs.
As shown in fig. 1, a method for predicting the passage time of a crowd going up stairs comprises the following steps:
s101: building a three-dimensional simulation model of a stair scene;
the method comprises the steps of adopting individual motion simulation software based on a social force model to model the stairs in the subway station corresponding to a field scene, wherein a three-dimensional simulation model of the stairs is shown in figure 2.
It should be noted that the model can also be modeled for school stairs or stairs in other places.
S102: putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
as shown in fig. 3, in the simulation, the simulated individuals are placed in the simulation scene, and the slope, height, width, individual expected speed and radius, and the number of people are changed for multiple times, so as to obtain the time of the people in different groups of slopes, heights, widths, individual expected speeds and radii, and the number of people going up the stairs, i.e. the training set.
The method obtains the training set by changing the gradient, the height, the width, the individual expected speed and radius and the number of people in the simulation experiment for many times, and is characterized in that a three-dimensional simulation model of the stair scene constructed based on a social force model is used for simulation, the social force model can simulate the individual movement more accurately, and the reliability of the obtained data is high.
S103: training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
the atomic orbit search algorithm is based on the atomic orbit principle, simulates the action between electrons in atomic orbits to carry out iteration of solution, takes the weight and the threshold of a neural network obtained by the traditional BP neural network as the attribute of the electrons in the atomic orbits, and takes the error as the probability density function value of the corresponding electrons, wherein the calculation formula of the error is
Wherein n is p Is the number of output layer neurons, i is the number of sequences of output layer neurons, y i In order to be able to output the desired value,
for the actual output value, the actual output value and eachNeuron corresponding weight z i And a threshold value theta i It is related.
The process of training the model is as follows:
(1) Determining the number of input layer neurons and the number of output layer neurons of the BP neural network according to the number of the input features and the number of the predicted features; defining the number of hidden layers to be 1 according to Kolmogorov theorem, namely, a three-layer neural network is total, and determining the number of neurons in the hidden layers:
the number of the input features is the grade, height and width of the stairs, the expected speed and radius of pedestrians and the number of types of the crowd, and the number of the predicted features is 1, namely only the passing time of the crowd going up the stairs is predicted; kolmogorov's theorem states that three-layer neural networks can map nonlinear functions with arbitrary precision.
(2) Setting an initial weight and a threshold of the neural network:
and setting an initial weight and a threshold of the neural network according to the conventional BP neural network rule.
(3) Carrying out training by bringing the training set into a BP neural network to obtain a weight value, a threshold value and a corresponding error after the training is finished, namely finishing the training of the BP neural network once, and taking the result as an electron of a certain layer of the atomic orbit;
the training set data is brought into the traditional BP neural network to operate to obtain corresponding neural network weight, threshold and corresponding error which are optimized by learning of the traditional BP neural network, and the learning process consists of two processes of forward propagation of signals and backward propagation of the error:
when the signal is transmitted in the forward direction, the training set data is transmitted from the input layer, processed layer by the hidden layer and transmitted to the output layer; and if the difference between the actual output and the expected output of the output layer exceeds a threshold value, performing back propagation on the steering error.
In the error back propagation stage, the output error is reversely transmitted to the input layer by layer through the hidden layer, and the error is distributed to all units (neurons) of each layer, so that an error signal of each layer of units (neurons) is obtained, and the error signal is used as a basis for correcting the weight of each unit (neuron); the basic principle of back propagation is to use a gradient descent method to find weights of units (neurons), so that the difference between actual output and expected output is minimized.
(4) Repeating the training of the BP neural network for o times to obtain o groups of weights, thresholds and corresponding errors for completing the training, so as to obtain o electrons, and forming all candidate solutions in each layer of the atomic orbit:
multiple groups of weights, thresholds and corresponding errors are obtained by operating the traditional BP neural network for multiple times, and multiple electrons, also called candidate solutions, are obtained.
(5) And taking the v candidate solutions as candidate solutions in a certain layer of the atomic orbit, and calculating to obtain a candidate solution corresponding to the highest probability density function value (the minimum value of the objective function), namely the optimal weight and the optimal threshold of the model.
And (3) taking the obtained weight and threshold as electronic attributes in an atomic orbit search algorithm, taking the error as a corresponding probability density function value, and iterating the weight and threshold of the neural network through the atomic orbit search algorithm until the optimal weight and threshold are found.
The atomic orbit search algorithm is a metaheuristic optimization algorithm based on quantum mechanics, wherein a search space in the algorithm is regarded as an electron cloud around an atomic nucleus, and the atomic nucleus is divided into thin and spherical concentric layers; most optimization algorithms implement the optimization process through iteration of a population of candidate solutions, and the atomic trajectory search algorithm also considers some of the candidate solutions Z, which represent electrons around atomic nuclei in a quantum-based atomic model.
In the invention, the candidate solution is formed by the weight z of the BP neural network i And a threshold value theta i The composition is as follows:
where o is the number of solution candidates, z i Is the weight, θ, corresponding to each cell i D is z for each cell corresponding threshold i R is theta i Number of solution candidates per group Z i Represented by a set of BP neural networks corresponding weights and thresholds to define the bits of the candidate solution in the search spaceAnd (4) placing.
Based on quantum atomic model, each candidate solution has an energy state, which is E, i.e. data error obtained by BP neural network training.
The vector equation Q is used to include the objective function values of the different candidate solutions, and the expression is:
wherein, E i Is the energy level of the ith candidate solution, i.e. the difference between the actual output and the expected output corresponding to the ith candidate solution;
in the quantum atomic model, the position of electrons around an atomic nucleus is determined by an electron probability density map, the electron probability density map is obtained by calculating a probability density function, and the probability density function of a variable represents the possibility that the variable is in a specific range; by considering layers created in a virtual manner around the atomic nucleus, the probability density function values corresponding to the candidate solutions are used to determine the positions of the candidate solutions in the layers;
the candidate solutions are ordered in ascending order (with the errors as small as possible), with candidate solutions with smaller objective function values being considered to have higher levels and probability density function values; the candidate solutions with higher probability density function values are located at the inner virtual electron layer, while the candidate solutions with lower probability density function values are located at the outer virtual electron layer; the electronic position is determined according to a probability density function, and each virtual layer contains a plurality of candidate solutions.
Assuming that v is the number of times of operating the BP neural network, v groups of weights and thresholds can be obtained by operating the BP neural network v times and are used as initial positions of candidate solutions, v corresponding energy states and position vectors (Z) of the candidate solutions in the virtual layer p ) And an objective function value (E) P ) The formula of (1) is as follows:
wherein,
is the ith candidate solution in the p virtual layer, d is the total weight corresponding to the BP neural network, r is the total threshold corresponding to the BP neural network, a is the maximum layer number of the virtual layer, v is the total number of the candidate solutions in the p virtual layer,
is the objective function value of the ith solution candidate in the p-th virtual layer.
Determining the binding state and binding energy of the candidate solution in a virtual layer by considering the positions of all candidate solutions in a certain layer and the average value of the objective function values; the binding state of the p-th layer electrons (solution candidates) is:
wherein, BS p Is the binding state of the p-th layer electrons (solution candidates), i is the sequence number of the electron;
the binding energy of the p-th layer electrons (solution candidates) is:
wherein BE p Binding energy for p-th layer electrons (solution candidates);
similarly, the binding state and binding energy of the atom are determined by searching the average of the positions of all candidate solutions and the objective function value in the space, and the binding state is:
the binding energy is:
to simulate the effect of photons on electrons around a nucleus, a uniformly distributed random number is generated for each candidate solution in the range of (0,1)
At the same time, the photon rate PR is taken into account as a probability parameter for the photon to electron effect.
When the temperature is higher than the set temperature
When considering electron motion between different layers around the nucleus, depending on the emission and absorption of photons, if any
Then the photon emission is considered, when the future position of the p-th layer candidate solution
And the current position
The relationship of (1) is:
where LE is the solution candidate of the lowest energy level, α l 、β l And σ 1 Is a uniformly distributed and randomly generated number vector in the range of (0,1) for determining the energy released.
If it is
Then the future position of the p-th layer candidate solution at this time is considered for photon absorption
And the current position
The relationship of (1) is:
if it is
The future position of the p-th layer candidate solution is considered to be the position where the photon does not contribute to the electron
And the current position
The relationship of (c) is:
wherein, mu i For random generation, a vector of numbers uniformly distributed within (0,1).
And (4) finding the optimal weight and the threshold value through the iteration of the formula, thus obtaining the model which completes the training.
S104: and inputting the grade, height, width, individual expected speed and radius of the stairs to be predicted and the number of the crowds into the trained model to obtain the predicted value of the passing time of the corresponding crowds ascending along the stairs.
The mean square error of the predicted value is reduced by 15 percent compared with that of a BP neural network, and the prediction precision can be improved by at least 21 percent compared with a support vector machine method and a fitting method.
Example two
The embodiment discloses a system for predicting the passing time of a crowd ascending along a stair;
as shown in fig. 4, a system for predicting the passage time of a crowd going upstairs includes a model building module, a training set building module, a model training module and a prediction result module;
a model building module configured to: building a three-dimensional simulation model of a stair scene;
a training set construction module configured to: putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
a model training module configured to: training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
a prediction results module configured to: and inputting the gradient, height, width, individual expected speed and radius of the stairs to be predicted and the number of the crowds into the trained model to obtain the passage time of the corresponding crowds going up the stairs.
EXAMPLE III
An object of the present embodiments is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, implements the steps in a method for predicting a transit time for a group of people to travel up stairs according to embodiment 1 of the present disclosure.
Example four
An object of the present embodiment is to provide an electronic device.
Electronic equipment, including memory, processor and program that is stored on the memory and can be executed on the processor, the processor when executing the program realizes the steps in the method for predicting the passage time of people going upstairs along stairs according to embodiment 1 of the present disclosure.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for predicting the passing time of a crowd going up stairs is characterized by comprising the following steps:
building a three-dimensional simulation model of a stair scene;
putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
and inputting the gradient, height, width, individual expected speed and radius of the stair to be predicted and the number of the crowd to be predicted into the trained model to obtain the passing time of the corresponding crowd going up the stair.
2. The method for predicting the passing time of the crowd going upstairs according to claim 1, wherein a three-dimensional simulation model of a stair scene is constructed by adopting individual motion simulation software based on a social force model.
3. The method as claimed in claim 1, wherein the simulation of the plurality of scenes comprises changing the slope, height, width, individual expected speed and radius of the stairs and the number of the crowd to obtain the corresponding passing time.
4. The method according to claim 1, wherein the atomic orbit search algorithm is based on an atomic orbit principle, and simulates the effect between electrons in an atomic orbit to iterate a solution, wherein a neural network weight and a threshold obtained by a conventional BP neural network are used as attributes of the electrons in the atomic orbit, and an error is used as a probability density function value of the corresponding electron.
5. The method for predicting the passage time of the crowd going upstairs according to claim 4, wherein a BP neural network model optimized by an atomic orbit search algorithm is trained, and the method specifically comprises the following steps:
(1) Determining the number of input layer neurons and the number of output layer neurons of the BP neural network according to the number of the input features and the number of the predicted features, defining the number of hidden layer layers to be 1 according to the Kolmogorov theorem, and determining the number of neurons in the hidden layers, namely, a total three-layer neural network;
(2) Setting an initial weight and a threshold of a neural network;
(3) Carrying out training by bringing the training set into a BP neural network to obtain a weight value, a threshold value and a corresponding error after the training is finished, namely finishing the training of the BP neural network once, and taking the result as an electron of a certain layer of the atomic orbit;
(4) Repeating the training of the BP neural network for o times to obtain o groups of weights, thresholds and corresponding errors for completing the training, so as to obtain o electrons to form all candidate solutions in each layer of the atomic orbit;
(5) And taking the v candidate solutions as candidate solutions in a certain layer of the atomic orbit, and calculating to obtain a candidate solution corresponding to the highest probability density function value (the minimum value of the objective function), namely the optimal weight and the optimal threshold of the model, thereby completing the training of the model.
6. The method as claimed in claim 5, wherein the number of the input features is the number of the stair slope, the height, the width, the expected speed and radius of the pedestrian and the number of the crowd, and the number of the predicted features is 1, that is, only the time of the crowd going up the stairs is predicted.
7. The method of claim 5, wherein the Kolmogorov theorem indicates that the three-layer neural network can map the non-linear function with any degree of accuracy.
8. A system for predicting the passage time of a crowd going up along stairs is characterized by comprising a model construction module, a training set construction module, a model training module and a prediction result module;
a model building module configured to: building a three-dimensional simulation model of a stair scene;
a training set construction module configured to: putting the simulation individuals into a three-dimensional simulation model, simulating various scenes, and constructing a training set of a BP neural network model;
a model training module configured to: training the BP neural network model optimized by the atomic orbit search algorithm by using a training set to obtain a trained model;
a prediction results module configured to: and inputting the gradient, height, width, individual expected speed and radius of the stair to be predicted and the number of the crowd to be predicted into the trained model to obtain the passing time of the corresponding crowd going up the stair.
9. Computer-readable storage medium, on which a program is stored which, when being executed by a processor, carries out the steps of a method for predicting the transit time of a group of people ascending stairs according to any one of claims 1 to 7.
10. Electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of a method for predicting the transit time of a person along stairs according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210982696.7A CN115270506B (en) | 2022-08-16 | 2022-08-16 | Method and system for predicting passing time of crowd ascending along stairs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210982696.7A CN115270506B (en) | 2022-08-16 | 2022-08-16 | Method and system for predicting passing time of crowd ascending along stairs |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115270506A true CN115270506A (en) | 2022-11-01 |
| CN115270506B CN115270506B (en) | 2024-02-23 |
Family
ID=83753283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210982696.7A Active CN115270506B (en) | 2022-08-16 | 2022-08-16 | Method and system for predicting passing time of crowd ascending along stairs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115270506B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090348A (en) * | 2023-02-09 | 2023-05-09 | 国网江苏省电力有限公司电力科学研究院 | Integrated learning estimation method, device and storage medium for feeder line loss |
| CN116401941A (en) * | 2023-03-27 | 2023-07-07 | 青岛理工大学 | Prediction method for evacuation capacity of subway station gate |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014164540A (en) * | 2013-02-26 | 2014-09-08 | Shimizu Corp | Evacuation action prediction system and evacuation action prediction program |
| CN109522876A (en) * | 2018-12-13 | 2019-03-26 | 北京交通大学 | Subway station building staircase selection prediction technique and system based on BP neural network |
| CN110046710A (en) * | 2019-04-11 | 2019-07-23 | 山东师范大学 | A kind of the nonlinear function Extremal optimization method and system of neural network |
| CN110956684A (en) * | 2019-11-27 | 2020-04-03 | 山东师范大学 | Crowd movement evacuation simulation method and system based on residual error network |
| CN111262858A (en) * | 2020-01-16 | 2020-06-09 | 郑州轻工业大学 | Network security situation prediction method based on SA _ SOA _ BP neural network |
| CN114169505A (en) * | 2021-12-10 | 2022-03-11 | 天津科技大学 | Method and system for training yield prediction model and related equipment |
| CN114330659A (en) * | 2021-12-29 | 2022-04-12 | 辽宁工程技术大学 | BP neural network parameter optimization method based on improved ASO algorithm |
| WO2022077587A1 (en) * | 2020-10-14 | 2022-04-21 | 深圳大学 | Data prediction method and apparatus, and terminal device |
| CN114818203A (en) * | 2022-06-06 | 2022-07-29 | 大连大学 | Reducer design method based on SWA algorithm |
-
2022
- 2022-08-16 CN CN202210982696.7A patent/CN115270506B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014164540A (en) * | 2013-02-26 | 2014-09-08 | Shimizu Corp | Evacuation action prediction system and evacuation action prediction program |
| CN109522876A (en) * | 2018-12-13 | 2019-03-26 | 北京交通大学 | Subway station building staircase selection prediction technique and system based on BP neural network |
| CN110046710A (en) * | 2019-04-11 | 2019-07-23 | 山东师范大学 | A kind of the nonlinear function Extremal optimization method and system of neural network |
| CN110956684A (en) * | 2019-11-27 | 2020-04-03 | 山东师范大学 | Crowd movement evacuation simulation method and system based on residual error network |
| CN111262858A (en) * | 2020-01-16 | 2020-06-09 | 郑州轻工业大学 | Network security situation prediction method based on SA _ SOA _ BP neural network |
| WO2022077587A1 (en) * | 2020-10-14 | 2022-04-21 | 深圳大学 | Data prediction method and apparatus, and terminal device |
| CN114169505A (en) * | 2021-12-10 | 2022-03-11 | 天津科技大学 | Method and system for training yield prediction model and related equipment |
| CN114330659A (en) * | 2021-12-29 | 2022-04-12 | 辽宁工程技术大学 | BP neural network parameter optimization method based on improved ASO algorithm |
| CN114818203A (en) * | 2022-06-06 | 2022-07-29 | 大连大学 | Reducer design method based on SWA algorithm |
Non-Patent Citations (5)
| Title |
|---|
| YANG, XIAOXIA: "Guide optimization in pedestrian emergency evacuation", APPLIED MATHEMATICS AND COMPUTATION, vol. 2020 * |
| 张秀国;: "人群运动仿真模型分析", 计算机时代, no. 11 * |
| 徐斌;刘弘;: "融合社会力与人工蜂群的人群疏散仿真方法", 小型微型计算机系统, no. 08, pages 1725 - 1729 * |
| 杨业: "城市轨道交通枢纽楼梯通行能力计算与仿真", 中国优秀硕士学位论文全文数据库, pages 39 - 52 * |
| 杨奕等: "基于遗传算法的BP神经网络在公交车到站时间预测中的应用", 《现代商业》, vol. 2017, no. 16, pages 38 - 40 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090348A (en) * | 2023-02-09 | 2023-05-09 | 国网江苏省电力有限公司电力科学研究院 | Integrated learning estimation method, device and storage medium for feeder line loss |
| CN116090348B (en) * | 2023-02-09 | 2023-11-24 | 国网江苏省电力有限公司电力科学研究院 | Integrated learning estimation method, device and storage medium for feeder line loss |
| CN116401941A (en) * | 2023-03-27 | 2023-07-07 | 青岛理工大学 | Prediction method for evacuation capacity of subway station gate |
| CN116401941B (en) * | 2023-03-27 | 2024-02-02 | 青岛理工大学 | Prediction method for evacuation capacity of subway station gate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115270506B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113110592B (en) | Unmanned aerial vehicle obstacle avoidance and path planning method | |
| CN115270506B (en) | Method and system for predicting passing time of crowd ascending along stairs | |
| CN111260118B (en) | Vehicle networking traffic flow prediction method based on quantum particle swarm optimization strategy | |
| CN112541302B (en) | Air quality prediction model training method, air quality prediction method and device | |
| CN108985515B (en) | New energy output prediction method and system based on independent cyclic neural network | |
| CN112216108A (en) | Traffic prediction method based on attribute-enhanced space-time graph convolution model | |
| CN116187608B (en) | Underground traffic facility evacuation path decision method, system and equipment in flood environment | |
| He et al. | Research on a novel combination system on the basis of deep learning and swarm intelligence optimization algorithm for wind speed forecasting | |
| CN106910337A (en) | A kind of traffic flow forecasting method based on glowworm swarm algorithm Yu RBF neural | |
| CN110164129B (en) | Single-intersection multi-lane traffic flow prediction method based on GERNN | |
| CN110473592A (en) | The multi-angle of view mankind for having supervision based on figure convolutional network cooperate with lethal gene prediction technique | |
| CN112784362A (en) | Hybrid optimization method and system for unmanned aerial vehicle-assisted edge calculation | |
| CN114202122A (en) | Urban traffic flow prediction method based on Markov cluster map attention network | |
| CN112230675A (en) | Unmanned aerial vehicle task allocation method considering operation environment and performance in collaborative search and rescue | |
| CN116401941B (en) | Prediction method for evacuation capacity of subway station gate | |
| CN114461931A (en) | User trajectory prediction method and system based on multi-relation fusion analysis | |
| Das et al. | Evolving fuzzy reasoning approach using a novel nature-inspired optimization tool | |
| CN115438842A (en) | Load prediction method based on adaptive improved dayflies and BP neural network | |
| Yang et al. | Multi-objective optimization of evacuation route for heterogeneous passengers in the metro station considering node efficiency | |
| CN112633591B (en) | Space searching method and device based on deep reinforcement learning | |
| Chu | A computer model for selecting facility evacuation design using cellular automata | |
| Korbmacher et al. | Differences in pedestrian trajectory predictions for high-and low-density situations | |
| Wen et al. | Hierarchical Sarsa learning based route guidance algorithm | |
| Huang et al. | A Matrix Translation Model for Evacuation Path Optimization | |
| Masliakova | Optimal routing and charging procedures for electric buses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |